A new wave of electric vehicles for personal mobility is currently crowding public spaces.They offer a sustainable and efficient way of getting around in urban environments,however,these devices bring additional safet...A new wave of electric vehicles for personal mobility is currently crowding public spaces.They offer a sustainable and efficient way of getting around in urban environments,however,these devices bring additional safety issues,including serious accidents for riders.Thereby,taking advantage of a connected personal mobility vehicle,we present a novel on-device Machine Learning(ML)-based fall detection system that analyzes data captured from a range of sensors integrated on an on-board unit(OBU)prototype.Given the typical processing limitations of these elements,we exploit the potential of the TinyML paradigm,which enables embedding powerful ML algorithms in constrained units.We have generated and publicly released a large dataset,including real riding measurements and realistically simulated falling events,which has been employed to produce different TinyML models.The attained results show the good operation of the system to detect falls efficiently using embedded OBUs.The considered algorithms have been successfully tested on mass-market low-power units,implying reduced energy consumption,flash footprints and running times,enabling new possibilities for this kind of vehicles.展开更多
On-board measurements of unit emissions of CO,HC,NOx and CO2 were conducted on 17 private cars powered by different types of fuels including gasoline,dual gasoline–liquefied petroleum gas（LPG）,gasoline,and diesel. ...On-board measurements of unit emissions of CO,HC,NOx and CO2 were conducted on 17 private cars powered by different types of fuels including gasoline,dual gasoline–liquefied petroleum gas（LPG）,gasoline,and diesel. The tests performed revealed the effect of LPG injection technology on unit emissions and made it possible to compare the measured emissions to the European Artemis emission model. A sequential multipoint injection LPG kit with no catalyst installed was found to be the most efficient pollutant reduction device for all of the pollutants,with the exception of the NOx. Specific test results for a sub-group of LPG vehicles revealed that LPG-fueled engines with no catalyst cannot compete with catalyzed gasoline and diesel engines. Vehicle age does not appear to be a determining parameter with regard to vehicle pollutant emissions. A fuel switch to LPG offers many advantages as far as pollutant emissions are concerned,due to LPG＇s intrinsic characteristics.However,these advantages are being rapidly offset by the strong development of both gasoline and diesel engine technologies and catalyst converters. The LPG＇s performance on a chassis dynamometer under real driving conditions was better than expected. The enforcement of pollutant emission standards in developing countries is an important step towards introducing clean technology and reducing vehicle emissions.展开更多
基金This work has been supported by the Spanish Ministry of Science,Innovation and Universities,under the Ramon y Cajal Program(ref.RYC-2017-23823)the projects ONOFRE 3(ref.PID2020-112675RB)and Go2Edge(ref.RED2018-102585-T)+1 种基金by the European Commission,under the 5G-MOBIX(ref.825496)projectby the Spanish Ministry for the Ecological Transition and the Demographic Challenge,under the MECANO project(ref.PGE-MOVES-SING-2019-000104).
文摘A new wave of electric vehicles for personal mobility is currently crowding public spaces.They offer a sustainable and efficient way of getting around in urban environments,however,these devices bring additional safety issues,including serious accidents for riders.Thereby,taking advantage of a connected personal mobility vehicle,we present a novel on-device Machine Learning(ML)-based fall detection system that analyzes data captured from a range of sensors integrated on an on-board unit(OBU)prototype.Given the typical processing limitations of these elements,we exploit the potential of the TinyML paradigm,which enables embedding powerful ML algorithms in constrained units.We have generated and publicly released a large dataset,including real riding measurements and realistically simulated falling events,which has been employed to produce different TinyML models.The attained results show the good operation of the system to detect falls efficiently using embedded OBUs.The considered algorithms have been successfully tested on mass-market low-power units,implying reduced energy consumption,flash footprints and running times,enabling new possibilities for this kind of vehicles.
文摘On-board measurements of unit emissions of CO,HC,NOx and CO2 were conducted on 17 private cars powered by different types of fuels including gasoline,dual gasoline–liquefied petroleum gas（LPG）,gasoline,and diesel. The tests performed revealed the effect of LPG injection technology on unit emissions and made it possible to compare the measured emissions to the European Artemis emission model. A sequential multipoint injection LPG kit with no catalyst installed was found to be the most efficient pollutant reduction device for all of the pollutants,with the exception of the NOx. Specific test results for a sub-group of LPG vehicles revealed that LPG-fueled engines with no catalyst cannot compete with catalyzed gasoline and diesel engines. Vehicle age does not appear to be a determining parameter with regard to vehicle pollutant emissions. A fuel switch to LPG offers many advantages as far as pollutant emissions are concerned,due to LPG＇s intrinsic characteristics.However,these advantages are being rapidly offset by the strong development of both gasoline and diesel engine technologies and catalyst converters. The LPG＇s performance on a chassis dynamometer under real driving conditions was better than expected. The enforcement of pollutant emission standards in developing countries is an important step towards introducing clean technology and reducing vehicle emissions.
